Search research articles

Related Concept Videos

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Automatic Segmentation of Bone Marrow Lesions on MRI Using a Deep Learning Method.

Bioengineering (Basel, Switzerland)·2024

See all related articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Oct 6, 2025

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Fully Automatic Knee Bone Detection and Segmentation on Three-Dimensional MRI.

Rania Almajalid^1,2, Ming Zhang^3,4, Juan Shan¹

¹Department of Computer Science, Seidenberg School of CSIS, Pace University, New York, NY 10038, USA.

Diagnostics (Basel, Switzerland)

|January 21, 2022

Summary

This summary is machine-generated.

A modified U-net model accurately segments knee bones from 3D MRI scans. This automated approach enhances osteoarthritis research by improving bone structure identification in medical imaging.

Keywords:

3D MRI U-net convolutional neural networks fully automatic bone detection and bone segmentation knee osteoarthritis

More Related Videos

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue

Published on: November 27, 2017

Related Experiment Videos

Last Updated: Oct 6, 2025

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue

3D Ultrasound Imaging: Fast and Cost-effective Morphometry of Musculoskeletal Tissue

Published on: November 27, 2017

Area of Science:

Medical Imaging
Artificial Intelligence
Orthopedics

Background:

Three-dimensional (3D) magnetic resonance imaging (MRI) is crucial for studying knee joint structures in osteoarthritis.
Accurate segmentation of bone structures in 3D MRI aids in analyzing soft tissues like cartilage and meniscus.
Existing U-net models, designed for 2D images, require adaptation for 3D volumetric data.

Purpose of the Study:

To develop a fully automatic model for detecting and segmenting knee bone structures from 3D MRI scans.
To adapt the U-net convolutional neural network for processing sequences of 2D MRI slices as 3D data.
To evaluate the performance of the proposed model against state-of-the-art segmentation methods.

Main Methods:

A modified U-net model was developed to process 3D MRI data, treating it as a sequence of 2D slices.
The model first detects the initial and final bone-containing slices and then segments bones in intermediate slices.
Training and validation were performed on 99 knee MRI cases, each with 160 slices, using metrics like Dice Coefficient (DICE) and similarity.

Main Results:

The bone detection model achieved 98.79% accuracy on the testing set.
The segmentation model attained a DICE score of 96.94% and a similarity score of 93.98%.
The proposed method demonstrated superior performance compared to U-net, SegNet, and FCN-8 in terms of DICE score.

Conclusions:

The developed automated model effectively detects and segments knee bone structures from 3D MRI.
This approach offers a significant improvement over existing methods for 3D knee MRI analysis.
The enhanced segmentation accuracy holds promise for advancing osteoarthritis research and diagnosis.